error-handler-gen
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it directly interpolates user-controlled CLI arguments into the LLM prompt.
- Ingestion points: The
frameworkandlangvariables are taken from CLI arguments insrc/cli.tsand passed to the generation function. - Boundary markers: None. The inputs are placed directly into the prompt strings in
src/index.tsanddist/index.jswithout delimiters or defensive instructions. - Capability inventory: The skill has the ability to write files to the local system (user-provided path) and make network requests to the OpenAI API.
- Sanitization: No validation against an allow-list or escaping is performed on the arguments before they are used to build the final prompt for the OpenAI API.
Audit Metadata